Medical imaging spans diverse tasks and modalities which play a pivotal role in disease diagnosis, treatment planning, and monitoring. This study presents a novel exploration, being the first to systematically evaluate segmentation, registration, and classification tasks across multiple imaging modalities. Integrating both classical and deep learning (DL) approaches in addressing brain MRI tissue segmentation, lung CT image registration, and skin lesion classification from dermoscopic images, we demonstrate the complementary strengths of these methodologies in diverse applications. For brain tissue segmentation, 3D DL models outperformed 2D and patch-based models, specifically nnU-Net achieving Dice of 0.9397, with 3D U-Net models on ResNet34 backbone, offering competitive results with Dice 0.8946. Multi-Atlas methods provided robust alternatives for cases where DL methods are not feasible, achieving average Dice of 0.7267. In lung CT registration, classical Elastix-based methods outperformed DL models, achieving a minimum Target Registration Error (TRE) of 6.68 mm, highlighting the effectiveness of parameter tuning. HighResNet performed best among DL models with a TRE of 7.40 mm. For skin lesion classification, ensembles of DL models like InceptionResNetV2 and ResNet50 excelled, achieving up to 90.44%, and 93.62% accuracies for binary and multiclass classification respectively. Also, adopting One-vs-All method, DL attained accuracies of 94.64% (mel vs. others), 95.35% (bcc vs. others), and 96.93% (scc vs. others), while ML models specifically Multi-Layer Perceptron (MLP) on handcrafted features offered interpretable alternatives with 85.04% accuracy using SMOTE for class imbalance correction on the multi-class task and 83.27% on the binary-class task. Links to source code are available on request.

翻译：医学影像涵盖多种任务与模态，在疾病诊断、治疗规划及监测中发挥着关键作用。本研究提出了一项新颖的探索，首次系统性地评估了跨多种成像模态的分割、配准与分类任务。通过整合经典方法与深度学习（DL）方法，分别针对脑部MRI组织分割、肺部CT图像配准以及皮肤镜图像的皮肤病变分类问题展开研究，我们展示了这些方法在不同应用场景中的互补优势。在脑组织分割任务中，3D深度学习模型的表现优于2D及基于图像块的模型，其中nnU-Net的Dice系数达到0.9397；基于ResNet34骨干网络的3D U-Net模型也取得了具有竞争力的结果，Dice系数为0.8946。在深度学习模型不适用的情况下，多图谱方法提供了可靠的替代方案，平均Dice系数达到0.7267。在肺部CT图像配准任务中，基于经典Elastix的方法优于深度学习模型，实现了6.68 mm的最小目标配准误差（TRE），凸显了参数调优的有效性。在深度学习模型中，HighResNet表现最佳，TRE为7.40 mm。在皮肤病变分类任务中，集成深度学习模型（如InceptionResNetV2与ResNet50）表现优异，在二分类与多分类任务中分别达到了90.44%与93.62%的准确率。此外，采用“一对多”方法时，深度学习模型在黑色素瘤（mel）与其他类别、基底细胞癌（bcc）与其他类别、鳞状细胞癌（scc）与其他类别的分类中分别取得了94.64%、95.35%与96.93%的准确率。同时，基于手工特征的机器学习模型（特别是多层感知机MLP）提供了可解释的替代方案：在多分类任务中，使用SMOTE处理类别不平衡后准确率达到85.04%；在二分类任务中准确率为83.27%。源代码链接可应要求提供。