Medgemma 1.5 4b, useful?

Hmm… It doesn’t seem like there’s a single place where all those people gather, but there are a few promising spots:

---

For your case , I think the best answer is:

The serious melanoma / skin-cancer ML people are mostly not in one giant always-on forum. They are spread across ISIC , Kaggle ISIC challenge discussions , the ISIC Workshop / MICCAI medical-imaging ecosystem , and a smaller number of GitHub / benchmark / working-group communities. Those are the places where the real signal is. (ISIC)

My read on your situation

Your project is already in a serious zone. Your repo describes an EVA-02 Small dermoscopy classifier for binary malignant vs benign screening , trained on a curated multi-source ISIC-style dataset, with a held-out test set of 6,384 images and reported operating points including about 97.01% sensitivity / 82.56% specificity and 95.02% sensitivity / 88.46% specificity depending on threshold. That is not a toy result. It means you are already past the “can I train a decent lesion classifier?” stage and into the harder stage: does it generalize, calibrate, and hold up in tougher settings? (GitHub)

That is also why MedGemma likely felt disappointing. You were comparing a focused dermoscopy screening model against a broad medical multimodal foundation model. Those are different tools. If your goal is “how risky is this mole?”, your closest comparators are not general medical chat models; they are specialized systems like ADAE , dermatology foundation models like Derm Foundation , and newer dermatology foundation-model work like PanDerm. (GitHub)

Where people actually gather

1. ISIC is the closest thing to a home base

If you only follow one ecosystem, follow ISIC. Its AI Working Group explicitly says it is focused on systems for melanoma diagnosis and clinical decision support , and it says its AI challenge ecosystem has inspired over 1,000 scientific papers. The public ISIC forum has categories for Events & Workshops, ISIC Challenge announcements , ISIC Archive , and ISIC Live Challenge , which makes it the closest thing to a dedicated skin-imaging AI forum. (ISIC)

What ISIC is good for:

• official challenge announcements
• archive / dataset questions
• benchmark infrastructure
• finding who is active in this exact niche. (ISIC Forum)

What it is not:

• it is not a giant informal chat room
• it is more structured and official than Discord-like. (ISIC Forum)

2. Kaggle ISIC discussions are where practitioners expose their methods

For seeing what strong builders are doing right now , Kaggle is one of the best places. The ISIC 2024 Skin Cancer Detection with 3D-TBP competition focuses on identifying malignant lesions from crops extracted from 3D total-body photography , and the official dataset site says the training set is 400,000 skin-lesion crops. Competition discussions and linked solution writeups are where you tend to see:

• baseline comparisons
• leaderboard ablations
• model-family choices
• augmentation and preprocessing tricks
• metric interpretation
• code links. (Kaggle)

For your project, this matters because Kaggle gives you the most practical view of the field’s current engineering frontier, especially if you want to know “what are good people actually trying?” rather than just “what is published?” (Kaggle)

3. The ISIC Workshop at MICCAI is where the serious research conversation happens

The ISIC Workshop @ MICCAI is one of the best places to monitor if you want to know what advanced skin-image-analysis researchers care about. The workshop explicitly positions itself as a venue for advancing skin-image analysis, and the 2024 workshop proceedings include topics like multimodal diagnosis, incomplete multimodal learning, and clinically relevant image-analysis problems. The MICCAI program book also places ISIC within the broader MICCAI ecosystem, which is one of the main global communities for medical image computing. (ISIC Archive Workshop)

This matters because your next problems are likely to be the same ones they are discussing:

• generalization
• uncertainty
• multimodality
• class imbalance
• fairness
• clinically useful risk stratification. (ISIC Archive Workshop)

4. Broader but still relevant: MICCAI and MLCommons Medical AI

If you want a broader umbrella beyond dermatology-specific spaces, MICCAI itself is worth following; the society describes itself as attracting world-leading scientists, engineers, and clinicians in medical image computing. Also, MLCommons Medical AI is useful as a broader open benchmark / best-practices community; its working-group page explicitly says it develops benchmarks and best practices for healthcare AI and lists GitHub and Discord as ways to connect. (MICCAI)

That said, for melanoma ML specifically , I would treat MLCommons as a useful broad-medical-AI side community, not the main place where skin-cancer specialists gather. The highest signal for your problem still seems to be ISIC + Kaggle + MICCAI workshop activity. (ISIC)

5. Discords: my honest view

I did not find a clearly dominant, high-signal, melanoma-specific Discord that I would put on the same level as the communities above. The strongest concrete Discord-style lead I found was the MLCommons Medical AI working group, which explicitly lists a Discord, but that is a broad healthcare-AI community rather than a skin-cancer-ML hub. So if you want the best return on time, I would put formal challenge and workshop ecosystems first , and Discord second. (MLCommons)

Where the bar is for your kind of problem

This is the part that matters most.

Bar 1: strong retrospective dermoscopy model

You are already around this bar. Your current repo is a legitimate retrospective dermoscopy screening model with solid reported operating points. This is good work. Many people never get this far. (GitHub)

Bar 2: external and prospective robustness

This is the harder bar, and it is the one that separates strong benchmark work from stronger translational work. The PROVE-AI prospective validation of ADAE reported 96.8% sensitivity but only 37.4% specificity at the prespecified 95%-sensitivity threshold. A separate prospective multicenter study tested an AI tool on data from eight hospitals with different cameras and rare melanoma types, highlighting exactly the kind of heterogeneity that matters in real practice. (Nature)

That is the background for my main point: your current 97/82-type operating point is promising, but the next important question is not “can I get 0.5% more AUROC?” It is “how much of this survives site shift, patient shift, camera shift, subtype shift, and prospective workflow constraints?” (GitHub)

Bar 3: triage / risk-surfacing workflows

The field is also moving beyond single-lesion dermoscopy classification. ISIC 2024 is framed around malignant-lesion identification from 3D total-body-photography crops , and a follow-up paper reports top ISIC’24 model performance for melanoma classification as high as AUC 0.9704 with SE top-15 = 0.7908. That is a different style of benchmark: closer to triage and lesion surfacing than classic dermoscopy-only binary classification. (ISIC 2024 Challenge Dataset)

So there are really multiple bars:

• strong retrospective dermoscopy
• external / prospective dermoscopy
• teletriage / TBP lesion surfacing. (Nature)

My thoughts for your case specifically

I think your next best move is not to spend too much time trying to make MedGemma into a lesion-risk model. The more relevant comparison class for you is:

• ADAE as a strong public melanoma baseline
• Derm Foundation as a dermatology-specific embedding model for downstream classifiers
• PanDerm as a modern dermatology foundation-model direction. (GitHub)

Why I say that:

• ADAE is directly in your problem family: melanoma-focused, dermoscopy-oriented, and prospectively validated. (GitHub)
• Derm Foundation is explicitly designed to accelerate dermatology-image model building with embeddings, requiring less data and compute than training from scratch. That is a practical upgrade path for a project like yours. (Google for Developers)
• PanDerm is one of the strongest signs of where the field is going: a multimodal dermatology foundation model pretrained on over 2 million real-world images from 11 institutions across 4 modalities , evaluated on 28 benchmarks including skin-cancer screening and risk stratification. (Nature)

That trio is much closer to your actual problem than a general medical VLM. (GitHub)

The practical “where should I go?” answer

If I were in your position, I would do this:

Check weekly

• ISIC forum for announcements, archive issues, and challenge activity. (ISIC Forum)
• Kaggle ISIC challenge discussions for practical methods and writeups. (Kaggle)
• ISIC-Research GitHub org for official code, metrics, and challenge repos. The org exposes repos like ADAE and 2024-challenge-dataset. (GitHub)

Check monthly

• ISIC Workshop @ MICCAI papers and proceedings. (ISIC Archive Workshop)
• Derm Foundation updates and notebooks. (Google for Developers)
• PanDerm paper/repo ecosystem. (Nature)

Join as a side channel

• MLCommons Medical AI if you want a broader med-AI working group with Discord and benchmarks. (MLCommons)

My direct recommendation

For your exact project , I would anchor myself in this order:

1. ISIC ecosystem first
2. Kaggle ISIC challenge discussions second
3. MICCAI / ISIC workshop third
4. Derm Foundation / ADAE / PanDerm as benchmark and model-family references
5. MLCommons Medical AI as a broader side community. (ISIC)

That mix will tell you:

• what others are doing,
• what the bar is,
• and which next baselines actually matter for your model. (Nature)