Soumick

🚀 Honoured to mentor at the 7th @HarvardHSI Hackathon! Organised by the @HarvardChanSPH, this global event comes to #MIND, #Milan on 10 & 11 April, thanks to @LaStatale, @polimi, @humantechnopole & SIIAM. Let us rethink health systems together to create a lasting impact!

[4/4] Massive thanks to my fantastic co-authors , Hadya, Andreas and Oliver for the collaboration. 🤝 ​🔓 Read for free until 17 May 2026: authors.elsevier.com/a/1mrGU_L2Otso… 💻 Open-source code: github.com/soumickmj/GPMo… ​#ExplainableAI #MedicalImaging #BrainTumour #Neurocomputing

[3/4] 📊 Validated on two datasets, the models handled severe class imbalance robustly: 🏆 Peak F1-score (classification): 0.93 ✅ Tumour-only accuracy (classification): 98.74% (outperforming state-of-the-art glioma grading classifiers!) 🎯 Median Dice (segmentation): 0.728

[1/4] 📄 Excited to share that our new paper has been published in Neurocomputing (@Elsevier)! ​We introduce a weakly supervised framework for brain tumour segmentation using inherently explainable classification models. 🧠👇

@joaquinbarroso We recently faced the same issue with a paper in a reputed journal. Round 1: rev 1 and 2 ask for papers from certain authors. Round 2, rev1 and 2 never responded. New rev3 and rev4 did the same! Many of the recommended papers were completely unrelated to our work!

I'm so mad. Once again, got a paper accepted, but Ref2 wants me to add 4 references all having a single author in common, whereas Ref1 suggests 6 with another common author! This unethical behavior should be stopped by the editors. Should I say who those authors are? Thoughts?

🎉 Congratulations to our @C_Glastonbury Group on receiving a grant from FRRB to study the immune landscape of pancreatic #cancer. 🧬 The project will use AI & single-cell tech to improve immunotherapy in #PDAC humantechnopole.it/en/news/frrb-f…

[3/3] LUMEN pipeline offers a more accurate and detailed characterisation of vessel morphology than traditional 2D MIP analysis, providing a powerful open-source tool to advance research into the pathophysiology of CSVD Open-source pipeline: lnkd.in/eiPvhgb4 #ai #vessel

[1/3] LUMEN, a #DL pipeline for the 3D morphological analysis of lenticulostriate arteries from 7T MRI, published today by @ElsevierConnect, reseach lead by @li_rl574, an amazing collaboration with @CamStroke and @c_t_rodgers from @Cambridge_Uni ➡️ Paper: lnkd.in/et58aRt5

[2/3] Our "old" deep learning framework, #DS6, showed remarkable robustness. Originally developed for and trained on healthy data, it excelled on a challenging clinical dataset #CamSVD, surpassing the widely-used nnU-Net with superior sensitivity for detecting weak vessel signals

Kevin is proud to be one of us! ✨ 💙 #ProudToBeNapoli | #ForzaNapoliSempre | #WelcomeKevin

Forza Napoli Sempre 💙

Very proud of this awesome crew @humantechnopole #eshg2025

Delighted to announce that our latest work on learning inter-rater variability for robust probabilistic segmentation is now published in Medical Image Analysis. 🔗 authors.elsevier.com/a/1l5Ba4rfPmLe… #MedicalImaging #ProbabilisticSegmentation #vae #DeepLearning #MICCAI #AIInHealthcare

Quantum Leap in Computing! This breakthrough could revolutionise physics, AI, cryptography and many more fields! The future is quantum!

The HT community sends you their warmest holiday wishes in languages from every corner of the globe. 🌍💬 Here's to another year of groundbreaking research and innovation! 🌟

Thread of the world's most beautiful towns and villages at Christmas 🧵 1. Locorotondo, Italy

🎗️Every 10 min, a woman is killed in the world. ✋For the International Day for the Elimination of Violence Against Women, we want to highlight the #SignalForHelp, an internationally gesture that can save countless women’s lives. ❌There is #NoExcuse for violence against women!

It’s time for #AIxIA2024 If you’re attending and have an interest in autonomous driving or road scene understanding, don’t miss my talk tomorrow in Main Track – Session 1. I’ll also be presenting 2 lightning talks + posters on Wednesday during the final session of HC@AIxIA.

If anyone is curious about the potential malevolent uses of AI, here is a perfect example!