Update typos

Author: charlesbmi

BENCHMARKS.md

@@ -70,7 +70,7 @@ The benchmark job in our CI pipeline ([`test_gpu.yml`](https://github.com/Forest
 
 ## CUDA Optimizations
 
-mach optimize GPU memory access patterns to improve performance. For those interested in learning more about CUDA optimization, excellent resources include:
+mach optimizes GPU memory access patterns to improve performance. For those interested in learning more about CUDA optimization, excellent resources include:
 
 - [CUDA Crash Course](https://github.com/CoffeeBeforeArch/cuda_programming/) by CoffeeBeforeArch
 - [How CUDA Programming Works](https://www.nvidia.com/en-us/on-demand/session/gtcspring22-s41487/) - CUDA Architect presentation on CUDA best-practices
@@ -180,9 +180,9 @@ python tests/plot_scaling.py --output assets/benchmark-scaling.png
 
 ![Benchmark scaling workload size](assets/benchmark-scaling.svg)
 
-*FIgure: throughput is largely consistent across dataset sizes, except for an improvement for >=16 frames.*
+*Figure: throughput is largely consistent across dataset sizes, except for a small decrease for <16 frames.*
 
-## Performance suggestions
+## Performance Suggestions
 
 For Maximum Throughput:
 

README.md

@@ -85,9 +85,9 @@ We welcome [feature requests](https://github.com/Forest-Neurotech/mach/issues)!
 
 mach builds upon the excellent work of the ultrasound imaging community:
 
-* **[vbeam](https://github.com/magnusdk/vbeam)** - For educational examples and validation benchmarks
-* **[PyMUST](https://github.com/creatis-ULTIM/PyMUST) / [PICMUS](https://www.creatis.insa-lyon.fr/Challenge/IEEE_IUS_2016/)** - For standardized evaluation datasets
-* **Community contributors** - Gev and Qi for CUDA optimization guidance
+- **[vbeam](https://github.com/magnusdk/vbeam)** - For educational examples and validation benchmarks
+- **[PyMUST](https://github.com/creatis-ULTIM/PyMUST) / [PICMUS](https://www.creatis.insa-lyon.fr/Challenge/IEEE_IUS_2016/)** - For standardized evaluation datasets
+- **Community contributors** - Gev and Qi for CUDA optimization guidance
 
 ## Citation
 

examples/doppler.py

@@ -5,7 +5,7 @@
 This example demonstrates CUDA-accelerated ultrasound beamforming for power Doppler
 imaging using a rotating disk phantom dataset. We'll use the same dataset as the
 `PyMUST Doppler example <https://www.biomecardio.com/MUST/functions/html/iq2doppler_doc.html>`_
-and follow a similar workflow to the `ultraspy doppler tutorial <https://ultraspy.readthedocs.io/en/latest/examples/doppler.html>`_.
+and follow a similar workflow to the `ultraspy doppler tutorial`_.
 
 **Dataset Attribution:**
 The rotating disk data comes from PyMUST's example dataset [1]_, which contains ultrasound data
@@ -292,9 +292,9 @@
 #
 # **Expected results:**
 # The power Doppler image should show:
-# - **Bright circular region**: The rotating disk creates motion that appears bright
-# - **Dark background**: Static tissue appears dark in power Doppler
-# - **Spatial accuracy**: Disk location matches the physical phantom geometry
+# - **Bright circular region**: The rotating disk creates motion that appears bright.
+# - **Dark background**: Static tissue appears dark in power Doppler.
+# - **Spatial accuracy**: Disk location matches the physical phantom geometry.
 # - **Matches**: https://www.biomecardio.com/MUST/functions/html/iq2doppler_doc.html#7
 #
 # **Performance advantages:**

examples/plane_wave_compound.py

@@ -3,7 +3,7 @@
 ===================================================
 
 This example demonstrates plane wave compounding of data from the
-PICMUS challenge (Plane-wave Imaging Challenge in Medical UltraSound). PICMUS
+PICMUS challenge (Plane-wave Imaging Challenge in Medical Ultrasound). PICMUS
 provides standardized datasets for evaluating plane wave imaging algorithms.
 
 **Example overview:**