2016 — 2025
Biomedical imaging
Dermoscopy & melanoma bibliography first; then deep learning for biomedical imaging beyond lesions.
Automated melanoma screening from dermoscopy sits at the intersection of clinical risk and dataset reality: class imbalance, subtle visual cues, acquisition artifacts, and shifts between cameras and populations. The first bibliography is the publication thread on lesions and coupled XAI / augmentation I built with collaborators—from classical features through deep nets, NAS, self‑supervision, and bias‑aware work.
Dermoscopy & melanoma thread
2025
- A survey on bias in machine learning research
A. Mikołajczyk-Bareła, M. Grochowski · IEEE Access, vol. 14, pp. 3284–3311
- Targeted Data Augmentation for Improving Model Robustness
A. Mikołajczyk-Bareła, M. Ferlin, M. Grochowski · International Journal of Applied Mathematics and Computer Science, vol. 35, no. 1
2023
- Data augmentation and explainability for bias discovery and mitigation in deep learning
A. Mikołajczyk-Bareła · PhD thesis, arXiv:2308.09464
2022
- The (de)biasing effect of GAN-based augmentation methods on skin lesion images
A. Mikołajczyk, S. Majchrowska, S. Carrasco Limeros · MICCAI
2021
- Towards explainable classifiers using the counterfactual approach — global explanations for discovering bias in data
A. Mikołajczyk, M. Grochowski, A. Kwasigroch · Journal of Artificial Intelligence and Soft Computing Research, vol. 11, no. 1, pp. 51–67
2020
- Self-Supervised Learning to Increase the Performance of Skin Lesion Classification
A. Kwasigroch, M. Grochowski, A. Mikołajczyk · Electronics, vol. 9, no. 11
- Explainable AI for inspecting adversarial attacks on deep neural networks
Z. Klawikowska, A. Mikołajczyk, M. Grochowski · ICAISC (Springer LNCS)
- Neural Architecture Search for Skin Lesion Classification
A. Kwasigroch, M. Grochowski, A. Mikołajczyk · IEEE Access, vol. 8, pp. 9061–9071
2019
- Style transfer-based image synthesis as an efficient regularization technique in deep learning
A. Mikołajczyk, M. Grochowski · MMAR (also arXiv:1905.10974)
- Selected technical issues of deep neural networks for image classification purposes
M. Grochowski, A. Kwasigroch, A. Mikołajczyk · Bulletin of the Polish Academy of Sciences: Technical Sciences, vol. 67, no. 2, pp. 363–376
- Diagnosis of malignant melanoma by neural network ensemble-based system utilising hand-crafted skin lesion features
M. Grochowski, A. Mikołajczyk, A. Kwasigroch · Metrology and Measurement Systems, vol. 26, no. 1, pp. 65–80
2018
- Data augmentation for improving deep learning in image classification problem
A. Mikołajczyk, M. Grochowski · International Interdisciplinary PhD Workshop (IIPhDW), IEEE, pp. 117–122
- Optimal selection of input features and an accompanying neural network structure for the classification purposes — skin lesions case study
A. Mikołajczyk, M. Grochowski, A. Kwasigroch · MMAR, pp. 899–904
- Analiza istotności cech znamion skórnych dla celów diagnostyki czerniaka złośliwego
A. Mikołajczyk, M. Grochowski · Zeszyty Naukowe Wydziału Elektrotechniki i Automatyki Politechniki Gdańskiej
2017
- Deep neural networks approach to skin lesions classification — a comparative analysis
A. Kwasigroch, A. Mikołajczyk, M. Grochowski · MMAR, pp. 1069–1074
- Deep convolutional neural networks as a decision support tool in medical problems — malignant melanoma case study
A. Kwasigroch, A. Mikołajczyk, M. Grochowski · Polish Control Conference (Springer), pp. 848–856
- Intelligent system supporting diagnosis of malignant melanoma
A. Mikołajczyk, A. Kwasigroch, M. Grochowski · Polish Control Conference (Springer), pp. 828–837
2016
- Analiza znamion skórnych przy pomocy metod przetwarzania obrazu i algorytmów inteligencji obliczeniowej
A. Mikołajczyk-Bareła · Przemysłowy Instytut Automatyki i Pomiarów PIAP (doctoral work context)
- System wspomagający diagnostykę czerniaka złośliwego przy pomocy metod przetwarzania obrazu i algorytmów inteligencji obliczeniowej
A. Mikołajczyk, A. Kwasigroch, M. Grochowski · Zeszyty Naukowe Wydziału Elektrotechniki i Automatyki Politechniki Gdańskiej
Deep learning for biomedical imaging
The same period included collaborative deep learning on other biomedical modalities—MRI cerebral microbleeds, peripheral blood smears, and microscopy for abnormal erythrocytes. Same methods culture (segmentation, classifiers, careful validation) as the lesion line, but not the dermoscopy narrative; grouped here so that work stays visible.
2021
- A Comprehensive Analysis of Deep Neural-Based Cerebral Microbleeds Detection System
M.A. Ferlin, M. Grochowski, A. Kwasigroch, A. Mikołajczyk, E. Szurowska, M. Grzywińska, A. Sabisz · Electronics, vol. 10, no. 18, p. 2208
2019
- Machine Learning System for Automated Blood Smear Analysis
M. Grochowski, M. Wąsowicz, A. Mikołajczyk, M. Ficek, M. Kulka, M. Wróbel, M. Jędrzejewska-Szczerska et al. · Metrology and Measurement Systems, vol. 26, no. 1, pp. 81–93
2017
- Computer Aided Detection of Abnormal Erythrocytes
M. Wąsowicz, M. Grochowski, M. Kulka, A. Mikołajczyk, M. Ficek, K. Karpieńko, M. Cićkiewicz · International Society for Optics and Photonics (SPIE) conference proceedings