Overview

CSCI 3397/PSYC 3317 is an advanced undergraduate-level class organized around building a biomedical image analysis startup prototype. We move through four themes: image processing (weeks 1–4), deep learning (weeks 5–10), foundation models (weeks 11–13), and agentic systems (weeks 14–16).

Schedule



Staff & Office Hours


Theme Date Topic Materials Assignments

Theme 1: Image Processing

Image Basics
[Week 1]		 Mon, Jan. 12 Lec. 1: Introduction
What: Overview
Why: Motivation
How: Syllabus
lab0 out
Wed, Jan. 14 Lec. 2: Image Basics
core: light, object,camera, physics
natural image, microscopy, medical devices
Fri, Jan. 16 Lec. 3: Digital Image Basics
maths: matrix
code: python libraries
lab0 due
No Class (Martin Luther King, Jr. Day)
Filtering
[Week 2-3]		 Wed, Jan. 21 Lec. 4: Pixel-level Processing
intensity transforms, histogram ops
Fri, Jan. 23 Lec. 5: Patch-level Processing (Convolution)
filtering, padding
impulse/box/Gaussian; smoothing vs sharpening
Mon, Jan. 26 Lec. 6: Nonlinear Filtering
bilateral; correlation/SSD templates
  • [T] Chap. 4.3.1
 lab1 due
Applications
[Week 3-4]		 Wed, Jan. 28 Lec. 7: Image Transformation
Image transformation
Fri, Jan. 30 Lec. 8: Scale Invariant Feature Transformation (SIFT)
  • [T] Chap. 4.2.3, 5.1
Mon, Feb. 2 Lec. 9: Transformation Estimation
Linear regression, RANSAC
lab2 due
Wed, Feb. 4 Lec. 10: Image Segmentation
Why: drug discovery, connectomics What: semantic, instance, panoptic
Fri, Feb. 6 Lec. 11: Morphological Operation
threshold/CC/watershed; Dice/IoU; morphology
fp team sign-up due

Theme 2: Deep Learning

ML Pipeline
[Week 5]		 Mon, Feb. 9 Lec. 12: ML Basics
splits, leakage, metrics; baseline mindset
  • [F] Chap. 1.1
  • Coding: scikit-learn
 ps1 due
Wed, Feb. 11 Lec. 13: Unsupervised Learning
k-means, PCA; embeddings as features
lab3 due
Fri, Feb. 13 Lec. 14: Supervised Learning Basics
linear regression; basis functions; regularization
Optimization + Linear Models
[Week 6]		 Mon, Feb. 16 Lec. 15: Linear Classification
logistic regression; cross-entropy; calibration
  • [F] Chap. 4.1-4.3
Wed, Feb. 18 Lec. 16: Optimization & Generalization
SGD/Adam; schedules; overfitting controls
  • [F] Chap. 4.1-4.3
 lab4 due
ps2 out (deep learning)
Fri, Feb. 20 Lec. 17: Modern Software for ML
reproducibility, configs, testing, CI; experiment tracking
Neural Nets + CNNs
[Week 7]		 Mon, Feb. 23 Lec. 18: MLPs I
nonlinearities, softmax; capacity vs data
  • [F] Chap. 3.4, 4.5
Wed, Feb. 25 Lec. 19: MLPs II (Backprop in Practice)
training loops; dropout; debugging
  • [F] Chap. 3.4, 4.5
  • Coding: PyTorch training loops
 lab5 due
Fri, Feb. 27 Lec. 20: CNNs I
convolution/pooling; inductive bias
fp proposal due
No Class (Spring Vacation: Mar. 2–7)
CNN Applications
[Week 9]		 Mon, Mar. 9 Lec. 21: CNNs II (ResNet + Transfer Learning)
fine-tuning, augmentation, compute tips
  • [F] Chap. 4.6-4.7
  • Papers: ResNet
Wed, Mar. 11 Lec. 22: Data-centric Training
imbalance, label noise; error analysis
  • Paper: ConvNeXt (modern CNN training recipe)
  • Topics: augmentation, label smoothing, robustness
 lab6 due
Fri, Mar. 13 Lec. 23: Deep Segmentation (U-Net)
encoder-decoder; Dice/Focal losses
  • [F] Chap. 6.4
  • Paper: U-Net
 ps2 due
Modern Vision Models
[Week 10]		 Mon, Mar. 16 Lec. 24: Object Detection
R-CNN/YOLO/DETR; mAP/FROC
  • [F] Chap. 6.3
  • Transformer detection: DETR
Wed, Mar. 18 Lec. 25: WSI / Weak Labels (MIL)
tiling, MIL attention; pathology workflows
  • Weak labels + MIL survey/primer (TBA)
  • Pathology workflow: tiling → aggregation → slide-level prediction
 lab7 due
Fri, Mar. 20 Lec. 26: Attention & Vision Transformers
tokens, positional encodings; bridge to FMs
  • [F] Chap. 4.8-4.10, 5.3
  • Paper: ViT
 fp check-in (baseline)

Theme 3: Foundation Models

FM Basics
[Week 11]		 Mon, Mar. 23 Lec. 27: Foundation Models Overview
pretraining objectives; transfer; evaluation
  • Course notes: foundation models in biomedical imaging
  • References: SAM, CLIP, domain pretraining
 ps3 out (foundation models)
Wed, Mar. 25 Lec. 28: Self-Supervised Vision
contrastive + masked modeling (MAE/DINO ideas)
  • Masked modeling / contrastive learning (MAE/DINO) (TBA)
 lab8 due
Fri, Mar. 27 Lec. 29: Parameter-Efficient Tuning (PEFT)
adapters/LoRA; domain adaptation
  • PEFT: adapters / LoRA (TBA)
Promptable + Domain FMs
[Week 12]		 Mon, Mar. 30 Lec. 30: Promptable Segmentation
SAM-style interaction; labeling workflows
  • Promptable segmentation (SAM / MedSAM) (TBA)
Wed, Apr. 1 Lec. 31: Biomedical Vision FMs + Retrieval
embeddings, nearest neighbors; gigapixel issues
  • Embeddings + retrieval; evaluation under domain shift (TBA)
 lab9 due
No Class (Good Friday Apr. 3) / No Class (Easter Monday Apr. 6)
Multimodal + Generative FMs
[Week 13]		 Wed, Apr. 8 Lec. 32: Vision-Language Models in Biomed
image+text alignment; report/Q&A; PathChat pattern
ps3 due
Fri, Apr. 10 Lec. 33: Generative Models for Imaging
diffusion for augmentation/inpainting; synthetic data
  • Diffusion overview; synthetic data pitfalls
  • Reference: MIT 6.S978 generative models reading list

Theme 4: Agentic Systems

LLM Tooling + RAG
[Week 14]		 Mon, Apr. 13 Lec. 34: LLM Tooling for Imaging Products
prompting, structured outputs, tool calling
ps4 out (agentic systems)
Wed, Apr. 15 Lec. 35: RAG + Evaluation Harness
retrieval, citations; testing prompts/agents
lab10 due
Fri, Apr. 17 Lec. 36: Agents I
planner/executor; tool use; guardrails
  • Agent design patterns: tools, memory, planning (TBA)
No Class (Patriot's Day: Mon Apr. 20)
Agentic Systems
[Week 15]		 Tue, Apr. 21
(Mon class)		 Lec. 37: Agents II (Workflow Automation)
automate experiments; reports; ablations
  • Agentic workflow: run → evaluate → report → iterate (TBA)
Wed, Apr. 22 Lec. 38: Productization & Deployment
latency, monitoring, privacy; demo clinic
ps4 due
fp slide due

Final Projects

Presentation Fri, Apr. 24 Final Project: Presentation I
Mon, Apr. 27 Final Project: Presentation II
Wed, Apr. 29 Final Project: Presentation III + Wrap-up
Submission Sun, May. 10 Final project report/code fp report/code due
Instructor
Name Office hours
Donglai Wed 2:30-3:30pm @ 245 Beacon Rm. 528F, Thu 2:30-3:30pm on zoom
  • Office hours will take place in person (or Zoom if needed).


Course information

This is a challenging course and we are here to help you become a more-AI version of yourself. Please feel free to reach out if you need help in any form.

1. Get help (besides office hours)

  • Dropbox: The lecture pdfs will be uploaded to Dropbox (follow the link) and you can ask questions there by making comments on the slides directly.
  • Support: The university counseling services center provides a variety of programs and activities.
  • Accommodations for students with disabilities: If you are a student with a documented disability seeking reasonable accommodations in this course, please contact Kathy Duggan, (617) 552-8093, dugganka@bc.edu, at the Connors Family Learning Center regarding learning disabilities and ADHD, or Rory Stein, (617) 552-3470, steinr@bc.edu, in the Disability Services Office regarding all other types of disabilities, including temporary disabilities. Advance notice and appropriate documentation are required for accommodations.

2. Homework submission

All programming assignments are in Python on Colab, always due at midnight (11:59 pm) on the due date .
  • Install Colab on the browser: Sign in to your Google account, follow the [link] to the folder of assignments, click on *.ipynb, click on "Open with" and "Connect more apps", install "Colaboratory".
  • Submission: You need save a copy of the file in your own Google drive, so that you can save your edits. Afterwards, you can download the ipynb file and submit it to Canvas.
  • Lab (1 per week): Every lecture has a lab exercise to help you gain the hands-on understanding about the material. The lab on previous week's lectures is due on Wednesday. We will go through some code in class and you need to finish up the exercises.
  • Pset (4 in total): In each pset, we will build a working prototype for a biology lab or a healthcare startup.
  • Final project: (guideline) In lieu of a final exam, we'll have a final project. This project will be completed in small groups during the last weeks of the class. The direction for this project is open-ended: you can either choose from a list of project ideas that we distribute, or you can propose a topic of your own. A short project proposal will be due approximately halfway through the course. During the final exam period, you'll turn in a final report and give a short presentation. You may use an ongoing research work for your final project, as long it meets the requirements.

3. Academic policy

  • Late days: You'll have 10 late days each for labs and psets respectively over the course of the semester. Each time you use one, you may submit a homework assignment one day late without penalty. You are allowed to use multiple late days on a single assignment. For example, you can use all of your days at once to turn in one assignment a week late. You do not need to notify us when you use a late day; we'll deduct it automatically. If you run out of late days and still submit late, your assignment will be penalized at a rate of 10% per day. If you edit your assignment after the deadline, this will count as a late submission, and we'll use the revision time as the date of submission (after a short grace period of a few minutes). We will not provide additional late time, except under exceptional circumstances, and for these we'll require documentation (e.g., a doctor's note). Please note that the late days are provided to help you deal with minor setbacks, such as routine illness or injury, paper deadlines, interviews, and computer problems; these do not generally qualify for an additional extension.
  • Academic integrity: While you are encouraged to discuss homework assignments with other students, your programming work must be completed individually. You may not search for solutions online, or to use existing implementations of the algorithms in the assignments. Thus it is acceptable to learn from another student the general idea for writing program code to perform a particular task, or the technique for solving a mathematical problem, but unacceptable for two students to prepare their assignments together and submit what are essentially two copies of identical work. If you have any uncertainty about the application of this policy, please check with me. Failure to comply with these guidelines will be considered a violation of the University policies on academic integrity. Please make sure that you are familiar with these policies. We will use moss.pl tool to check each lab and pset for plagriasm detection.

4. Additional resource
Acknowledgements: This course is a biomedical version of CSCI 3343: Computer Vision with concrete biomedical image analysis applications. See the "Acknowledge" section in that class.

© 2026 Boston College. Website based on a template from HTML5 Up and Andrew Owen's course at U. Michigan.